Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer
Waiting for job on chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer to finish
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ _____ __ __ ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ /___/ ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ belonging to: ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ║ ║
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: Downloaded to shared memory in 52.363s
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_88zcpqb, device:0
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: quantized model in 36.861s
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: Processed model ChaiML/qwen14b-dpoexp2-sftdel12kexp1-v10v115kfilter in 89.225s
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-57126-v1
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-57126-v1/config.json
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-57126-v1/added_tokens.json
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-57126-v1/tokenizer_config.json
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-57126-v1/special_tokens_map.json
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-57126-v1/merges.txt
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-57126-v1/tokenizer.json
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-57126-v1/vocab.json
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen14b-dpoexp2-57126-v1/flywheel_model.0.safetensors
chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer:
Loading 0: 0%| | 0/579 [00:00<?, ?it/s]
Loading 0: 3%|▎ | 15/579 [00:00<00:04, 129.98it/s]
Loading 0: 5%|▍ | 28/579 [00:00<00:04, 123.94it/s]
Loading 0: 7%|▋ | 41/579 [00:00<00:04, 123.31it/s]
Loading 0: 10%|█ | 59/579 [00:00<00:03, 142.92it/s]
Loading 0: 13%|█▎ | 78/579 [00:00<00:03, 156.35it/s]
Loading 0: 16%|█▌ | 94/579 [00:00<00:05, 91.06it/s]
Loading 0: 18%|█▊ | 107/579 [00:00<00:04, 98.40it/s]
Loading 0: 21%|██ | 120/579 [00:01<00:04, 104.71it/s]
Loading 0: 24%|██▍ | 138/579 [00:01<00:03, 120.99it/s]
Loading 0: 27%|██▋ | 154/579 [00:01<00:03, 130.12it/s]
Loading 0: 29%|██▉ | 169/579 [00:01<00:03, 127.15it/s]
Loading 0: 32%|███▏ | 186/579 [00:01<00:02, 138.07it/s]
Loading 0: 35%|███▍ | 201/579 [00:01<00:04, 87.08it/s]
Loading 0: 38%|███▊ | 219/579 [00:01<00:03, 102.33it/s]
Loading 0: 40%|████ | 232/579 [00:02<00:03, 107.25it/s]
Loading 0: 42%|████▏ | 245/579 [00:02<00:02, 112.00it/s]
Loading 0: 46%|████▌ | 265/579 [00:02<00:02, 133.32it/s]
Loading 0: 48%|████▊ | 280/579 [00:02<00:02, 127.67it/s]
Loading 0: 51%|█████▏ | 297/579 [00:02<00:02, 100.27it/s]
Loading 0: 53%|█████▎ | 309/579 [00:02<00:02, 96.83it/s]
Loading 0: 56%|█████▋ | 327/579 [00:02<00:02, 111.52it/s]
Loading 0: 59%|█████▊ | 340/579 [00:02<00:02, 115.30it/s]
Loading 0: 61%|██████ | 353/579 [00:03<00:01, 118.04it/s]
Loading 0: 64%|██████▍ | 373/579 [00:03<00:01, 138.94it/s]
Loading 0: 67%|██████▋ | 388/579 [00:03<00:01, 134.24it/s]
Loading 0: 70%|██████▉ | 405/579 [00:03<00:01, 104.59it/s]
Loading 0: 72%|███████▏ | 417/579 [00:03<00:01, 99.72it/s]
Loading 0: 75%|███████▌ | 435/579 [00:03<00:01, 114.85it/s]
Loading 0: 77%|███████▋ | 448/579 [00:03<00:01, 118.02it/s]
Loading 0: 80%|███████▉ | 461/579 [00:04<00:00, 120.01it/s]
Loading 0: 83%|████████▎ | 481/579 [00:04<00:00, 141.06it/s]
Loading 0: 86%|████████▌ | 496/579 [00:04<00:00, 134.72it/s]
Loading 0: 88%|████████▊ | 512/579 [00:22<00:00, 134.72it/s]
Loading 0: 89%|████████▊ | 513/579 [00:26<00:27, 2.43it/s]
Loading 0: 90%|████████▉ | 521/579 [00:26<00:19, 2.93it/s]
Loading 0: 92%|█████████▏| 534/579 [00:26<00:11, 4.08it/s]
Loading 0: 95%|█████████▌| 552/579 [00:26<00:04, 6.33it/s]
Loading 0: 98%|█████████▊| 568/579 [00:26<00:01, 9.08it/s]
Job chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer completed after 114.77s with status: succeeded
Stopping job with name chaiml-qwen14b-dpoexp2-57126-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen14b-dpoexp2-57126-v1
Waiting for inference service chaiml-qwen14b-dpoexp2-57126-v1 to be ready
Inference service chaiml-qwen14b-dpoexp2-57126-v1 ready after 100.57659792900085s
Pipeline stage MKMLDeployer completed in 101.17s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7748513221740723s
Received healthy response to inference request in 1.9640436172485352s
Received healthy response to inference request in 1.9798228740692139s
Received healthy response to inference request in 2.2121996879577637s
Received healthy response to inference request in 1.95100998878479s
5 requests
0 failed requests
5th percentile: 1.9536167144775392
10th percentile: 1.956223440170288
20th percentile: 1.961436891555786
30th percentile: 1.9671994686126708
40th percentile: 1.9735111713409423
50th percentile: 1.9798228740692139
60th percentile: 2.0727735996246337
70th percentile: 2.1657243251800535
80th percentile: 2.3247300148010255
90th percentile: 2.5497906684875487
95th percentile: 2.6623209953308105
99th percentile: 2.75234525680542
mean time: 2.176385498046875
Pipeline stage StressChecker completed in 12.36s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.78s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.75s
Shutdown handler de-registered
chaiml-qwen14b-dpoexp2-_57126_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2606.35s
Shutdown handler de-registered
chaiml-qwen14b-dpoexp2-_57126_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen14b-dpoexp2-_57126_v1 status is now torndown due to DeploymentManager action